Zixuan Chen

Zixuan Chen 陈子璇

Postdoctoral Researcher
Yuxiu Young Scholar

School of Intelligent Science and Technology
Nanjing University
Suzhou, China

chenzx@nju.edu.cn
Scholar GitHub

About Me

Hi! I am Zixuan Chen (陈子璇). I received my Ph.D. degree from the School of Computer Science and Technology, Nanjing University (NJU) in March 2026, advised by Prof. Yang Gao and Assoc. Prof. Jing Huo. I have joined the School of Intelligent Science and Technology, Nanjing University (Suzhou Campus) as a Postdoctoral Researcher (Yuxiu Young Scholar).

Previously, I received my B.E. and M.E. degrees from Soochow University, School of Computer Science and Technology, under the supervision of Prof. Zongzhang Zhang. From Nov. 2024 to Nov. 2025, I was a visiting student at the National University of Singapore (NUS), working with Prof. Lin Shao.

Research Interests

My research focuses on Robot Learning, Reinforcement Learning, and Imitation Learning for embodied agents. I am particularly interested in three complementary directions, one target problem supported by two core capabilities:

News

  • 2026.09 Selected for the 2026 Jiangsu Young Science and Technology Talent Support Program.
    入选2026年江苏省青年科技人才托举工程。
  • 2026.09 Received the 2026 CCF Ph.D. Dissertation Incentive Award (recommended by the Technical Committee on Intelligent Robotics).
    获2026年度CCF博士学位论文激励计划（智能机器人专委会推荐）。
  • 2026.07 Recognized as a Yuxiu Young Scholar at Nanjing University.
  • 2026.07 Preprint "Wh0" (Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data) was released.
  • 2026.06 "INHerit-SG" was selected as a Best Presentation Finalist at the ICRA 2026 Workshop on Robots Meet Prior Maps.
  • 2026.06 "RoboHorizon" was accepted to SCIENCE CHINA Information Sciences (SCIS).
  • 2026.06 "V-Dreamer" received the Best Paper Award at the ICRA 2026 Workshop on Generative Digital Twins for Real2Sim and Sim2Real Transfer.
  • 2026.04 Invited talk at Zhuoyu Technology (卓驭科技), Shenzhen, China.
  • 2026.02 "AGiLe" was accepted to CVPR 2026.
  • 2026.01 4 papers (RoTri-Diff, LaViRA, AdaptPNP and LISN) were accepted to ICRA 2026.
  • 2026.01 "DeCo" was accepted to RAL 2026.
  • 2025.11 "ManiLong-Shot" was accepted to AAAI 2026.
  • 2025.10 Preprint "RoboHiMan" (Compositional Generalization in Long-horizon Manipulation) was released.
  • 2025.05 Preprint "DeCo" (Task Decomposition and Skill Composition for Long-horizon Manipulation) was released.
  • 2025.01 "GravMAD" was accepted to ICLR 2025.
  • 2025.01 Preprint "RoboHorizon" (World Model for Long-horizon Manipulation) was released.
  • 2024.09 "SCaR" (Skill Chaining) was accepted to NeurIPS 2024.
  • 2023.12 "Cognizing and Imitating Robotic Skills" was accepted to AAMAS 2024.
  • 2023.01 "TiLD" was accepted to AAMAS 2023.

Selected Publications

(* equal contribution)

2026

  1. AGiLe: Learning Robust Long-Horizon Manipulation via Affordance-Grounded Bidirectional Latent Planning
    Zixuan Chen, Xiangrong Feng, Jieqi Shi, Lin Shao, Jing Huo, Yang Gao.
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
    PDF Website
  2. RoTri-Diff: A Spatial Robot-Object Triadic Interaction-Guided Diffusion Model for Bimanual Manipulation
    Zixuan Chen, Nga Teng Chan, Yiwen Hou, Chenrui Tie, Zixuan Liu, Haonan Chen, Junting Chen, Jieqi Shi, Yang Gao, Jing Huo, Lin Shao.
    IEEE International Conference on Robotics and Automation (ICRA), 2026.
    PDF
  3. DeCo: Task Decomposition and Skill Composition for Zero-Shot Generalization in Long-Horizon 3D Manipulation
    Zixuan Chen, Junhui Yin, Yangtao Chen, Jing Huo, Pinzhuo Tian, Jieqi Shi, Yiwen Hou, Yinchuan Li, Yang Gao.
    IEEE Robotics and Automation Letters (RAL), 2026.
    PDF Website Code
  4. ManiLong-Shot: Interaction-Aware One-Shot Imitation Learning for Long-Horizon Manipulation
    Zixuan Chen, Chongkai Gao, Lin Shao, Jieqi Shi, Jing Huo, Yang Gao.
    AAAI Conference on Artificial Intelligence (AAAI), 2026.
    PDF
  5. RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic Manipulation
    Zixuan Chen, Jing Huo, Yangtao Chen, Yang Gao.
    SCIENCE CHINA Information Sciences (SCIS), 2026.
    PDF
  6. INHerit-SG: Incremental Hierarchical Semantic Scene Graphs with RAG-Style Retrieval
    YukTung Samuel Fang, Zhikang Shi, Jiabin Qiu, Zixuan Chen, Jieqi Shi, Hao Xu, Jing Huo, Yang Gao.
    arXiv preprint arXiv:2602.12971, 2026. (Best Presentation Finalist, ICRA 2026 Workshop on Robots Meet Prior Maps)
    PDF Website
  7. Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data
    Yangtao Chen*, Zixuan Chen*, Peiyang Wang*, Yong-Lu Li, Jing Huo, Jieqi Shi, Yang Gao.
    arXiv preprint arXiv:2606.22136, 2026.
    PDF Website Code
  8. AdaClearGrasp: Learning Adaptive Clearing for Zero-Shot Robust Dexterous Grasping in Densely Cluttered Environments
    Zixuan Chen*, W. Zhang*, J. Fang, R. Zeng, Z. Xu, Y. Hou, X. Wang, Jieqi Shi, Jing Huo, et al.
    arXiv preprint arXiv:2603.10616, 2026.
    PDF Website Code
  9. V-Dreamer: Automating Robotic Simulation and Trajectory Synthesis via Video Generation Priors
    Songjia He*, Zixuan Chen*, Hongyu Ding, D. Shao, Jieqi Shi, C. Li, Jing Huo, Yang Gao.
    arXiv preprint arXiv:2603.18811, 2026. (Best Paper Award, ICRA 2026 Workshop on Generative Digital Twins for Real2Sim and Sim2Real Transfer)
    PDF
  10. ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation
    Y. Wu*, Zixuan Chen*, C. Ou, W. Wang, W. Huang, L. Cao, Y. Chen, W. Qiu, X. Quan, et al.
    arXiv preprint arXiv:2603.13788, 2026.
    PDF
  11. MoMaStage: Skill-State Graph Guided Planning and Closed-Loop Execution for Long-Horizon Indoor Mobile Manipulation
    C. Li*, Zixuan Chen*, Y. Li, J. Xu, Hongyu Ding, Jieqi Shi, Jing Huo, Yang Gao.
    arXiv preprint arXiv:2603.08383, 2026.
    PDF
  12. Uni-LaViRA: Language-Vision-Robot Actions Translation for Unified Embodied Navigation
    Hongyu Ding, S. Zhang, Z. Xu, J. Guo, H. Liu, X. Cheng, Zixuan Chen, H. Qi, D. Wang, et al.
    arXiv preprint arXiv:2605.27582, 2026.
    PDF

2025

  1. RoboHiMan: A Hierarchical Evaluation Paradigm for Compositional Generalization in Long-Horizon Manipulation
    Yangtao Chen*, Zixuan Chen*, Nga Teng Chan, Junting Chen, Junhui Yin, Jieqi Shi, Yang Gao, Yong-Lu Li, Jing Huo.
    arXiv preprint arXiv:2510.13149, 2025.
    PDF Website Code
  2. GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation
    Yangtao Chen*, Zixuan Chen*, Junhui Yin, Jing Huo, Pinzhuo Tian, Jieqi Shi, Yang Gao.
    International Conference on Learning Representations (ICLR), 2025.
    PDF Website

2024

  1. SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization
    Zixuan Chen, Ze Ji, Jing Huo, Yang Gao.
    Conference on Neural Information Processing Systems (NeurIPS), 2024.
    PDF
  2. Cognizing and Imitating Robotic Skills via a Dual Cognition-Action Architecture
    Zixuan Chen, Ze Ji, Shuyang Liu, Jing Huo, Yiyu Chen, Yang Gao.
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2024.
    PDF

2023

  1. TiLD: Third-person Imitation Learning by Estimating Domain Cognitive Differences of Visual Demonstrations
    Zixuan Chen, Wenbin Li, Yang Gao, Yiyu Chen.
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023.
    PDF

Honors and Awards

Services

Internships

Powered by Jekyll and Minimal Light theme.